Hacker News: dangoodmanUT

New comment by dangoodmanUT in "Show HN: Firefox in WebAssembly"

dangoodmanUT — Wed, 15 Jul 2026 23:17:29 +0000

25k tokens is a few turns

New comment by dangoodmanUT in "A global workspace in language models"

dangoodmanUT — Mon, 06 Jul 2026 21:09:55 +0000

J-space sounds oddly similar to...

New comment by dangoodmanUT in "Workers Cache"

dangoodmanUT — Mon, 06 Jul 2026 14:12:27 +0000

finally, this was needed.

A big worry was always "why does workers sit in front of my cache? that's a waste of an invocation if i'm returning a cached result"

Show HN: Tinysandbox – An ultra-minimal sandbox with QuickJS WASM isolates

dangoodmanUT — Sun, 05 Jul 2026 16:12:02 +0000

We needed hyper-lightweight sandboxes for massively parallel agent fanout that could be recycled in milliseconds, take only KBs of memory when not actively running a command, and can work with bottomless filesystems.

Tinysandbox is like just-bash, but supports a minimal secure JS runtime via QuickJS WASM, random file IO, VFS checkpoint and restore, and streaming IO for working with large files.

It's designed for super-lightweight agents that don't need full linux, but still need the emergent behavior of shell commands and script writing to complete their task.

Comments URL: https://news.ycombinator.com/item?id=48795380

Points: 4

# Comments: 0

New comment by dangoodmanUT in "crustc: entirety of `rustc`, translated to C"

dangoodmanUT — Fri, 03 Jul 2026 00:25:31 +0000

i believe the author is confused

this is the wrong direction

(jk i read the readme)

New comment by dangoodmanUT in "Show HN: ZeroFS – A log-structured filesystem for S3"

dangoodmanUT — Thu, 02 Jul 2026 19:05:18 +0000

If you actually bench it locally (local S3, actually writes to disk for "staged" operations), ZeroFS performs horrifically. Ceph blows it out of the water. I don't have the exact numbers, but when I was building a toy CoW distributed block device and filesystem I did a perf matrix, and ZeroFS (even with an hour of codex tuning it) was never within the same 1 or 2 orders of magnitude perf-wise.

Sure, Ceph isn't "S3-backed", but when you're talking about an actual filesystem or block device (the thing that does lots of small-IO), you care more about io-perf than sequential.

Large sequential jobs that everyone is targeting now (ie AI workloads) can use s3 directly just fine, because they don't have decades of code built on top of the filesystem.

New comment by dangoodmanUT in "Apertus – Open Foundation Model for Sovereign AI"

dangoodmanUT — Mon, 22 Jun 2026 00:16:27 +0000

How are they going to be competitive with top models at 70B size?

New comment by dangoodmanUT in "Iroh 1.0"

dangoodmanUT — Mon, 15 Jun 2026 17:25:31 +0000

iroh is consistently one of the most delightful projects i've ever worked with. The people reflect that too.

Congrats iroh team!

New comment by dangoodmanUT in "How to earn a billion dollars"

dangoodmanUT — Sun, 14 Jun 2026 13:29:35 +0000

These are actually the most durable businesses because they have network effects: restaurants alright signed up, sellers onboarded, etc.

Easier for them to adopt AI than AI companies to rebuild the networks

New comment by dangoodmanUT in "Claude Fable 5"

dangoodmanUT — Tue, 09 Jun 2026 18:06:11 +0000

Not comparing to GPT Pro models is a bit strange, considering that's the natural comparison

New comment by dangoodmanUT in "Apple reveals new AI architecture built around Google Gemini models"

dangoodmanUT — Mon, 08 Jun 2026 20:58:35 +0000

I'm really not looking forward to Gemini models on my devices.

Gemini models clearly gaslight the user and hallucinate, they're also SUPER verbose, as shown in the demos from the keynote.

Plus, if they're not charging a subscription for this, you know we're getting the dumbest models...

New comment by dangoodmanUT in "Claude Opus 4.8"

dangoodmanUT — Thu, 28 May 2026 17:19:38 +0000

> The Messages API now accepts system entries inside the messages array. Developers can update Claude’s instructions mid-task without breaking the prompt cache or routing the update through a user turn. This can be used in a given harness to update permissions, token budgets, or environment context as an agent runs.

Biggest deal imo

New comment by dangoodmanUT in "Taking a walk may lead to more creativity than sitting, study finds (2014)"

dangoodmanUT — Tue, 26 May 2026 12:30:24 +0000

Exactly this

New comment by dangoodmanUT in "Incident Report: Railway Blocked by Google Cloud [resolved]"

dangoodmanUT — Wed, 20 May 2026 01:22:04 +0000

It has been 0 days since GCP has taken down a startup (again).

You see this at least once a year. Never heard of this from AWS or Azure.

In all seriousness, this is why we don't use them. They have the most ergonomic cloud of the big three, then absolutely murder it by having this kind of reputation.

New comment by dangoodmanUT in "Quack: The DuckDB Client-Server Protocol"

dangoodmanUT — Wed, 13 May 2026 00:12:47 +0000

This. Type casting is an insidious problem (both correctness, and perf)

New comment by dangoodmanUT in "Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model"

dangoodmanUT — Tue, 12 May 2026 21:54:19 +0000

Why pick Gemini? It's probably the worst tool calling model of the major labs.

New comment by dangoodmanUT in "YC's Biggest Scandals"

dangoodmanUT — Sun, 10 May 2026 21:23:37 +0000

Seems like AI slop. They list Rippling, and the description starts with Parker Conrad, but the rest of it is about Deel:

> Rippling

> Parker Conrad's redemption arc after Zenefits hit a plot twist when Rippling sued competitor Deel for planting an undercover spy inside Rippling who was paid €5,000/month by Deel's CEO to steal trade secrets. The DOJ opened a criminal investigation. Deel allegedly ran the same playbook at crypto HR startup Toku. YC uses Rippling for their own HR — awkward.

Per this description Rippling did nothing wrong here, all about Deel...

New comment by dangoodmanUT in "I returned to AWS, and was reminded why I left"

dangoodmanUT — Sun, 10 May 2026 13:35:14 +0000

GCP would be perfect if they didn't have a history of randomly dropping quotas on startups, causing them downtime

New comment by dangoodmanUT in "Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc"

dangoodmanUT — Sat, 09 May 2026 21:12:34 +0000

If this goes through, it feels like it will stoke rust on zig violence

New comment by dangoodmanUT in "An update on GitHub availability"

dangoodmanUT — Tue, 28 Apr 2026 12:33:26 +0000

Two incidents? Just two?

In seriousness, looking at their scale, this is an insane engineering challenge.

Especially if they’re moving databases, not easy ever, and certainly not at that scale